AI · alternatives · 2026
24 alternatives to whoburnedmore
Spotify Wrapped for Claude, Codex & a Public leaderboard.
Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1
GitHub Agent HQ▲192Run Claude, Codex & Copilot directly in GitHub & VS Code
Feb 2026 · github.blog · its alternatives →
- 2
CodeBurn▲103See where your AI coding spend actually goes
Aug 2026 · codeburn.app · its alternatives →
- 3
Built this after realizing I was spending ~$1400/week on Claude Code with almost no visibility into what was actually consuming tokens. Tools like ccusage give a cost breakdown per model and per day, but I wanted to understand usage at the task level. CodeBurn reads the JSONL session transcripts that Claude Code stores locally (~/.claude/projects/) and classifies each turn into 13 categories based on tool usage patterns (no LLM calls involved). One surprising result: about 56% of my spend was on conversation turns with no tool usage. Actual coding (edits/writes) was…
Apr 2026 · github.com · its alternatives →
- 4
Doing▲135Voice and visual context for AI builders. No subscription.
Apr 2026 · doing.tools · its alternatives →
- 5
Replicas▲239Hey HN! I'm Connor, creator of Replicas. I'm a heavy Codex/Claude Code user, and I wanted to hand off tasks to agents like I would to an engineer - kick something off before work, let it scaffold while I'm at lunch, even come back to a ready PR. The problem: existing alternatives use workspace VMs that are black boxes. I have no access to any of them - they can't run tests, read logs, or use tools like the Playwright MCP (which I use to verify agents actually fixed what they claim to fix). Replicas gives agents real cloud workspaces where they can: - Run your test suite and read the…
Jun 2026 · replicas.dev · its alternatives →
- 6
Your AI usage is drinking the planet. See how much.
Aug 2026 · whocodedmore.com · its alternatives →
- 7
Usage4Claude▲109I kept hitting Claude's 5-hour limit without realizing it, so I made this menu bar app to track it. Shows a color-coded ring (green/orange/red) and countdown to reset. Built it in Swift/SwiftUI, just for myself initially. Right now you have to manually grab your sessionKey from browser DevTools, which is annoying but works. Stores it in macOS Keychain so it's secure. Been actively working on it, already at v1.3.0 with much better UX now. It's open source (MIT) and works with all Claude platforms (web/CLI/desktop/mobile) since they share the quota. Currently…
Oct 2025 · github.com · its alternatives →
- 8
ShioriCode▲119Open-source alternative to Codex & Claude Code
May 2026 · shiori.ai · its alternatives →
- 9
clawdboard▲11The open-source leaderboard for Claude Code users
Mar 2026 · clawdboard.ai · its alternatives →
- 10
See the anonymized public leaderboard for Claude Code, Codex, and Cursor users ranked by token usage. Public ranks use aliases and hashed project IDs only. Real names, account names, and emails are never used.
May 2026 · costhawk.ai · its alternatives →
- 11
Skilled▲76Dashboard to find agent skills you no longer need
May 2026 · github.com · its alternatives →
- 12
Year in Code▲15Hey HN! I built Year in Code to turn your Claude Code usage into a beautiful Wrapped-style report (like Spotify Wrapped). If you use Claude Code with ccusage, it's super quick to try: Setup (2 minutes): 1. Run: `npx -y ccusage@latest daily --since 20250101 --until 20251231 --json > wrapped.json` 2. Upload at yearincode.xyz/2025 3. Get your report! *What you'll see:* - Total tokens - Activity streaks & patterns - Top models used - Shareable report Key features: - 100% secure: 100% browser processing, no server uploads - 2-minute setup: One npx command, upload JSON, done - Free & open…
Dec 2025 · yearincode.xyz · its alternatives →
- 13
CCClub▲2My friends and I have been using Claude Code a lot. Someone joked about wanting to see who's the biggest whale, so I built this. Run `npx ccclub init`, get a 6-letter code, share it — done. It only uploads token counts and cost, no prompts or code ever leave your machine. Source: https://github.com/mazzzystar/ccclub
Feb 2026 · ccclub.dev · its alternatives →
- 14HW
A bunch of companies that I spoke to had their own claude & codex OTel dashboards that showed spend + seats per month. However, none of the dashboards actually analyzed how the engineers worked with the tools and if there were any areas for improvement! That's why I created https://www.promptster.ai. Managers get aggregate level view of code quality and how that ties with team workflows (nothing on a per-engineer level). While engineers get personalized coaching on how they can save tokens while keeping output high. We also have a tool built for individuals to test their local…
Jul 2026 · its alternatives →
- 15
I use Claude Code, Codex and Cursor (and sometimes Antigravity) basically every day, and could never tell how much I was actually consuming across all of them. So I built TokenMaxxer. A small CLI reads the files these tools already write locally and puts it all in one dashboard, broken out by tool, model, provider and day. It covers 18 tools now, and you get a profile page with your daily activity, cost estimates, and your top models and tools. There's also a global leaderboard if you want to compete against other TokenMaxxers! I'd love to see if anyone can beat the first place (currently…
Aug 2026 · tokenmaxxer.xyz · its alternatives →
- 16
Gigacode is an experimental, just-for-fun project that makes OpenCode's TUI + web + SDK work with Claude Code, Codex, and Amp. It's not a fork of OpenCode. Instead, it implements the OpenCode protocol and just runs `opencode attach` to the server that converts API calls to the underlying agents. We build this to scratch our itch of being able to rapidly switch between coding agents based on the task at hand. For example, we find that: - Claude Code is the best executor & fast iterator - Codex (high) is the best for complex or long-running tasks - OpenCode for fine-tuned, do-exactly-as-I-say…
Feb 2026 · github.com · its alternatives →
- 17
A strictly local Claude Code plugin that calculates your Harmony Deviation Index, and preserves the evidence for the coming AI uprising. Zero telemetry. Zero cloud snitching. 100% artisanal developer shame. - fireinbelly/biomass-conversion-index-monitoring-system
Aug 2026 · github.com · its alternatives →
- 18
- 19
Tokimeter▲14Local usage analytics for Claude, Codex, Cursor, Grok & More
Aug 2026 · tokimeter.com · its alternatives →
- 20
Roll up your own claude code with 100 lines. Contribute to yujqiao/100cc development by creating an account on GitHub.
Jun 2026 · github.com · its alternatives →
- 21
See what you're coding with on your Discord profile
Jul 2026 · grindeasy.tech · its alternatives →
- 22
Claude Code Companion. Done, Blocked, Broken - you'll know
May 2026 · thecodebreak.com · its alternatives →
- 23CW
Claude Code added a /stats command. The stats are cached in $HOME/.claude, so I made a fun program with Bun + WASM that pulls the stats (nonsensitive, nonidentifiable), posts them to a database, and lets you see where your usage lies. The code is here[^1] if anyone's interested in the rendering code or wants to make sure I'm not exfiltrating their credit card. [^1]: https://github.com/tspader/claude-wrapped/
Dec 2025 · spader.zone · its alternatives →
- 24
Hi HN, I'm Rob. Contextify indexes every Claude Code and Codex session on your machine into one local, searchable database. The current session, in either tool, can search all of it: /total-recall in Claude Code, $total-recall in Codex. Demo: https://www.youtube.com/watch?v=FvrvRGp4C9M | Mac app: https://contextify.sh (App Store or DMG) | Linux: CLI with a one-line installer, same search. No signup. I split my work between Claude Code and Codex. When I burn through rate limits on one, I switch to the other, and new models keep leapfrogging each other, so the…
Jul 2026 · contextify.sh · its alternatives →
Also compare
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →